Lin Nana, Zhu Youxiang, Liang Xiaohui, Batsis John A, Summerour Caroline
University of Massachusetts Boston, MA, USA.
University of North Carolina, Chapel Hill, NC, USA.
Interspeech. 2024 Sep;2024:3030-3034. doi: 10.21437/interspeech.2024-2288.
Mild cognitive impairment (MCI) is a major public health concern due to its high risk of progressing to dementia. This study investigates the potential of detecting MCI with spontaneous voice assistant (VA) commands from 35 older adults in a controlled setting. Specifically, a command-generation task is designed with pre-defined intents for participants to freely generate commands that are more associated with cognitive ability than read commands. We develop MCI classification and regression models with audio, textual, intent, and multimodal fusion features. We find the command-generation task outperforms the command-reading task with an average classification accuracy of 82%, achieved by leveraging multimodal fusion features. In addition, generated commands correlate more strongly with memory and attention subdomains than read commands. Our results confirm the effectiveness of the command-generation task and imply the promise of using longitudinal in-home commands for MCI detection.
轻度认知障碍（MCI）因其发展为痴呆症的高风险而成为一个主要的公共卫生问题。本研究在可控环境中调查了利用35名老年人的自发语音助手（VA）指令来检测MCI的潜力。具体而言，设计了一个指令生成任务，为参与者设定了预定义意图，使其能够自由生成比朗读指令更能反映认知能力的指令。我们利用音频、文本、意图和多模态融合特征开发了MCI分类和回归模型。我们发现，通过利用多模态融合特征，指令生成任务的表现优于指令朗读任务，平均分类准确率达到82%。此外，生成的指令与记忆和注意力子领域的相关性比朗读指令更强。我们的结果证实了指令生成任务的有效性，并暗示了使用纵向家庭指令进行MCI检测的前景。
